DiegoT200's picture
First Push
0f82015 verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9281316995620728,
"min": 0.9281316995620728,
"max": 2.872858762741089,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8851.591796875,
"min": 8851.591796875,
"max": 29515.75,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.575582504272461,
"min": 0.4480891227722168,
"max": 12.575582504272461,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2452.238525390625,
"min": 86.92929077148438,
"max": 2512.476806640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07228762878010314,
"min": 0.06491472143291807,
"max": 0.07305263980807092,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28915051512041257,
"min": 0.2596588857316723,
"max": 0.3474657471059461,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18668362301062136,
"min": 0.106882851453288,
"max": 0.27777777867866493,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7467344920424854,
"min": 0.427531405813152,
"max": 1.3833926320075989,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.09090909090909,
"min": 2.9318181818181817,
"max": 25.163636363636364,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 129.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 2.9318181818181817,
"max": 25.163636363636364,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 129.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711833366",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711833952"
},
"total": 586.209415836,
"count": 1,
"self": 1.0019098019998864,
"children": {
"run_training.setup": {
"total": 0.07595322600002419,
"count": 1,
"self": 0.07595322600002419
},
"TrainerController.start_learning": {
"total": 585.131552808,
"count": 1,
"self": 0.9072384210031714,
"children": {
"TrainerController._reset_env": {
"total": 4.154172764999998,
"count": 1,
"self": 4.154172764999998
},
"TrainerController.advance": {
"total": 579.9248287299966,
"count": 18210,
"self": 0.42941266500679376,
"children": {
"env_step": {
"total": 579.4954160649899,
"count": 18210,
"self": 445.75960012999406,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.3120150360004,
"count": 18210,
"self": 2.3515743829999565,
"children": {
"TorchPolicy.evaluate": {
"total": 130.96044065300043,
"count": 18210,
"self": 130.96044065300043
}
}
},
"workers": {
"total": 0.4238008989954096,
"count": 18210,
"self": 0.0,
"children": {
"worker_root": {
"total": 583.089426111004,
"count": 18210,
"is_parallel": true,
"self": 269.14345248500297,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010399688999996215,
"count": 1,
"is_parallel": true,
"self": 0.007579096999961621,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002820592000034594,
"count": 10,
"is_parallel": true,
"self": 0.002820592000034594
}
}
},
"UnityEnvironment.step": {
"total": 0.04954248900003222,
"count": 1,
"is_parallel": true,
"self": 0.0009222440000939969,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004647250000289205,
"count": 1,
"is_parallel": true,
"self": 0.0004647250000289205
},
"communicator.exchange": {
"total": 0.04561536999995042,
"count": 1,
"is_parallel": true,
"self": 0.04561536999995042
},
"steps_from_proto": {
"total": 0.002540149999958885,
"count": 1,
"is_parallel": true,
"self": 0.00048396099998626596,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002056188999972619,
"count": 10,
"is_parallel": true,
"self": 0.002056188999972619
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 313.945973626001,
"count": 18209,
"is_parallel": true,
"self": 15.059894157985696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.542054055003973,
"count": 18209,
"is_parallel": true,
"self": 7.542054055003973
},
"communicator.exchange": {
"total": 246.22445938401097,
"count": 18209,
"is_parallel": true,
"self": 246.22445938401097
},
"steps_from_proto": {
"total": 45.11956602900034,
"count": 18209,
"is_parallel": true,
"self": 8.859171257017124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.260394771983215,
"count": 182090,
"is_parallel": true,
"self": 36.260394771983215
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024145200018210744,
"count": 1,
"self": 0.00024145200018210744,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 572.7232019860162,
"count": 834473,
"is_parallel": true,
"self": 18.48367987797269,
"children": {
"process_trajectory": {
"total": 324.0637674590431,
"count": 834473,
"is_parallel": true,
"self": 323.0651268900431,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9986405690000311,
"count": 4,
"is_parallel": true,
"self": 0.9986405690000311
}
}
},
"_update_policy": {
"total": 230.1757546490004,
"count": 90,
"is_parallel": true,
"self": 55.5414160779967,
"children": {
"TorchPPOOptimizer.update": {
"total": 174.6343385710037,
"count": 4587,
"is_parallel": true,
"self": 174.6343385710037
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1450714400000379,
"count": 1,
"self": 0.0038493609999932232,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1412220790000447,
"count": 1,
"self": 0.1412220790000447
}
}
}
}
}
}
}